Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to the specific embodiments of the present specification and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
At this stage, the identification of the electronic object to be authenticated, for example, the picture to be identified obtained according to the certificate to be authenticated, may be performed by the following method: the method comprises the steps of obtaining a picture to be identified according to an object to be authenticated, extracting identification features from the picture, classifying and identifying the picture according to the identification features, and further determining whether the object to be identified is from an original.
In the method, only by identifying the picture to be identified acquired according to the object to be authenticated, the identification information which can be acquired from the picture to be identified is limited, so that the identification effect is poor, and the accuracy of judgment is influenced.
The inventor finds that when an object to be authenticated is authenticated, the object to be authenticated needs to be photographed to obtain an electronic article to be authenticated, such as a picture to be recognized, and at this time, if the object to be authenticated is an electronic article forged from the object to be authenticated, such as a forged electronic certificate, after the forging is completed, the forged electronic article needs to be presented in a certain physical manner, for example, by screen display or print display, so that the picture to be recognized can be obtained by means of secondary copying and then input into an authentication system for authentication, therefore, the image recognition method, the device, the equipment, the authentication method, the device, and the equipment provided by the embodiments of the present specification make full use of the characteristic that the forged electronic article needs to be used for authentication by screen display or print display, and recognize the image to be recognized obtained by secondary copying according to the forged electronic article, the use of counterfeit electronic certificates in the authentication process is effectively prevented and controlled.
An application diagram of the image recognition process in the embodiment of the present specification may be as shown in fig. 1, and includes a target object 10 to be recognized, for example, an identification card, an identification mark 20, for example, a two-dimensional code, mapped on the target object, and a target image 30 obtained according to the target object 10 and the identification mark 20.
When the target image 30 is acquired, the target image 30 is acquired according to the target object 10 mapped with the identification mark 20, the target image 30 has the identification features formed according to the identification mark 20, after the target image 30 is acquired, the target image 30 is identified according to the identification features and a preset mapping relation, and then the attribute of the target object corresponding to the target image 30 is determined.
In a specific implementation, the mapping of the identification mark 20 and the acquisition, identification and determination of the target image 30 may be performed by the same subject or by different subjects.
The image recognition method provided by the embodiment of the present specification is executed by the same main body, for example, by a terminal, and the process is as follows:
the terminal maps the identification mark 20 on the identification object 10 to obtain the target image 30, identifies the target image 30 and determines the attribute of the target object corresponding to the target image 30.
The image recognition method provided by the embodiment of the present specification is executed by different subjects, for example, by a terminal and a server, and the process is as follows:
the identification mark 20 is mapped on the identification object 10 through the terminal, the target image 30 is obtained, the target image 30 is sent to the server for identification, and then the identification result is sent to the terminal to determine the attribute of the target object corresponding to the target image 30.
The above commonly performed process may also be that the first terminal maps the identification identifier 20 on the identification object 10, the second terminal obtains the target image 30, sends the target image 30 to the server for identification, and then sends the identification result to the second terminal to determine the attribute of the target object corresponding to the target image 30.
The terminal includes a terminal device capable of running software, including but not limited to a computer, a tablet computer, a mobile phone, a client device of a bank, and the like.
The overall idea of the image recognition method provided in the embodiments of this specification is that a counterfeit electronic part must be displayed through a screen display or a print display, so that the counterfeit electronic part and an original have different surface material characteristics, and by mapping a recognition mark on a target object, the recognition mark will generate a difference when being displayed on the target object based on the reason that the original and the counterfeit electronic part have different surface materials, and further when obtaining a target image corresponding to the target object with the recognition mark, the recognition mark can form a corresponding recognition feature on the target image, for example, the recognition feature may include a feature formed according to the difference generated by the recognition mark on the target object, so as to actively add the recognition feature to a recognition process, and finally based on the recognition feature actively added by the difference, through a trained mapping relationship, the attribute of the target object corresponding to the target image is determined, for example, the target image can be an image obtained according to an original or an image obtained according to a displayed forged electronic part, so that the identification accuracy of the target image is effectively improved.
The image recognition method provided by the embodiment of the specification acquires a target image of a target object, wherein before the target image is acquired, an identification mark is mapped on the target object and used for forming corresponding recognition features in the target image, differences generated by the identification mark on different types of target objects are fully utilized, the recognizable recognition features are formed on the target image based on the differences, abundant recognition information is provided for subsequent recognition, and meanwhile, the identification mark is set in a mapping mode, so that damage to the target object is avoided; and then, the attribute of the target object of the target image is identified according to the identification characteristics and the preset mapping relation, and identification judgment is carried out based on the identification characteristics, so that the identification accuracy is effectively improved. In the identification process, the characteristic which is easy to identify is actively added to the identification process in a mode of mapping the identification mark on the target object, and the picture is identified based on the newly added identification characteristic, so that the accuracy and the identification efficiency are improved, and the interference of irrelevant characteristics on the identification process and the identification result is avoided.
The above application scenarios are merely illustrated to facilitate understanding of the present application, and the embodiments of the present specification are not limited in any way in this respect. Rather, embodiments of the present description may be applied to any scenario where applicable.
Hereinafter, an image recognition method, an image recognition apparatus, an image recognition device, an authentication method, an authentication apparatus, and an authentication device according to the present specification will be described in detail with reference to the drawings.
Example 1
Fig. 2 is a flowchart of an image recognition method according to an embodiment of the present disclosure.
As shown in fig. 2, the image recognition method in the embodiment of the present specification includes the following steps:
in step S201, a target image of a target object is acquired.
Before the target image is obtained, an identification mark is mapped on the target object, and the identification mark is used for forming corresponding identification features in the target image.
In the embodiment of the present specification, the target object includes an object for generating a target image.
For example, in an application scenario where identity recognition is required, the target object may be a document used to characterize identity, such as an identification card, a driving license, a passport, etc., in which case the document may be an original of the document, and may also be an electronic element (e.g., a copy of the document) forged from the original.
For another example, in an application scenario where it is required to identify whether a bank card is actually held, the target object may also be a bank card in various forms, and in this case, the bank card may be an original of the bank card or an electronic component (e.g., a copy of the bank card) forged according to the original.
Note that the reproduction is a reproduction that is physically reproduced, for example, a reproduction for a screen display or a reproduction for a print display.
The identification mark includes a mark mapped on the target object for generating a feature for recognition, for example, the identification mark may be a specific pattern or the like.
In the actual operation process, the identification mark is mapped on the surface of the target object, light rays can be emitted outwards through a light source with the identification mark, when the target object is close to the identification mark, the light rays are reflected on the surface of the target object, and then the identification mark capable of forming identification characteristics is mapped on the surface of the target object.
The identification mapping method can adjust the identification according to actual needs, meet complex actual use requirements, avoid damage to the target object and simply, quickly and clearly set the identification on the target object.
The recognition feature includes a feature that can be recognized, which corresponds to the recognition mark, formed in the target image.
Specifically, the target object for obtaining the target image has different surface materials according to the difference of the target object, and therefore, when the identification mark is mapped on the target object, the identification mark may be different on different surfaces due to the difference of the surface materials. For example, when the target object is an original document of an identification card, the surface material is an anti-counterfeiting coating film, when the target object is a reproduction piece of the identification card displayed on a screen, the surface material is a liquid crystal display screen, at the moment, the identification marks can generate obvious differences on the surfaces of two different materials, the identification features corresponding to the identification marks in the acquired target image can keep the differences, and then the identification features can be used for identification based on the differences.
In an application example, in order to perform recognition more accurately, the recognition mark includes a pattern including a positioning feature, and the positioning feature is used for positioning the pattern including the positioning feature.
For example, the pattern including the positioning features may be a circular pattern, a centrosymmetric polygonal pattern, or the like.
The pattern containing the positioning features is adopted as the identification mark, so that the identification mark can be positioned based on the positioning features in the subsequent identification process, the position of the identification features is determined, and the identification features can be more accurately and quickly used for identification.
In this embodiment of the present specification, the obtained target image includes a target object and an identification feature corresponding to the identification identifier.
In the practical application process, in order to obtain the target image simply, quickly and quickly, the method of obtaining the target image may include shooting and obtaining, for example, shooting the target object and the identification mark by using a camera, for example, shooting a picture or a video, and obtaining one picture in the shot picture or video as the target image; scanning acquisition may also be included, for example, scanning the target object and the identification mark with a scanner, and acquiring the scanned image as a target image.
Further, the identification features in the acquired target image include any one or more of color features, texture features, shape features and spatial relationship features.
For example, when the target object is an identification card, and the identification features are displayed on an identification card original and an identification card reproduction piece displayed on a screen or printed and displayed, due to the difference of surface materials of the original and the screen or paper reproduction piece, the identification marks mapped on the original can generate differences in gray scale and color, differences in texture, deformation differences in outline, differences in relative position with the identification card, and the like, and the identification marks can form corresponding identification features on the target image based on the differences.
In an application example, in order to enable the whole recognition process to be convenient to operate and avoid using complex equipment, the image recognition method in the embodiment of the specification can be used in a mobile terminal, and the mobile terminal comprises a display unit and an image acquisition unit;
the step of acquiring a target image of a target object includes:
acquiring a target image through an image acquisition unit;
the step of mapping the identification on the target object comprises:
mapping, by the display unit, the recognition identifier presented on the display unit on the target object;
the image acquisition unit and the display unit are positioned on the same side of the target object.
In the embodiments of the present specification, the mobile terminal may include a mobile phone, a tablet, a computer, a bank client, or other mobile devices capable of displaying an image and performing image acquisition.
The display unit is used for presenting the identification mark and mapping the identification mark to the target object.
The identification marks may comprise randomly generated identification marks, such as circular icons, square icons and the like; it may also be an identification mark containing preset specific information, such as a trademark, an abbreviation, a two-dimensional code, a barcode, a number, or the like.
The presentation of the identification by the display unit may comprise displaying the same identification, for example fixedly displaying an abbreviation of a bank as the identification; the identification mark may also be displayed according to a predetermined display strategy, for example, different two-dimensional codes are displayed according to a predetermined period.
The identification mark can be displayed in various display modes, can flexibly adapt to different application scenes, and can well meet different setting requirements.
The image acquisition unit is used for acquiring a target image according to the target object and the identification mark mapped on the target object.
Specifically, in the process of acquiring a target image by the mobile terminal, the image display unit displays a preset identification mark and is used as a light source to map the identification mark on the target object, at this time, because the acquisition direction of the target image acquired by the image acquisition unit is positioned on the same side as the direction in which the identification mark is mapped on the target object by the display unit, the image acquisition unit can shoot the target object mapped with the identification mark, and then the target image is acquired.
The image acquisition unit and the display unit are positioned on the same side of the target object, so that the setting of the identification and the acquisition of the target image can be completed in one mobile terminal, the use of redundant equipment is avoided, and the operation is simple and convenient.
In an application example, in order to make the authentication process more convenient and flexible, the mobile terminal comprises a mobile intelligent device, the display unit comprises a screen, the image acquisition unit comprises a front camera,
acquiring the target image by the image acquisition unit includes:
acquiring a target image through a front camera;
mapping, by the display unit, the recognition mark presented on the display unit on the target object includes:
the identification displayed on the screen is mapped on the target object through the screen.
In this embodiment, the mobile smart device may include a mobile phone, a tablet, or another mobile smart device capable of displaying an image and performing image acquisition.
Fig. 3 is a schematic diagram illustrating an image of an identity card acquired by a mobile phone in an image recognition method provided in an embodiment of the present specification.
Specifically, the acquisition of a target image of an identity card is performed by a mobile phone as an example, wherein the display unit is a mobile phone screen, the image acquisition unit is a front-end camera of the mobile phone, the target object is an identity card copying part (i.e. an identity card displayed on a screen), the identification mark is a two-dimensional code, as shown in fig. 3, the front-end camera of the mobile phone and the mobile phone screen are located on the same side of the identity card, at this time, the mobile phone can be held to shoot the identity card displayed on the screen, the two-dimensional code is mapped to the surface of the identity card copying part through the two-dimensional code displayed on the mobile phone screen, so that the two-dimensional code appears on the surface of the identity card copying part (as shown in a dotted frame in fig. 3), at this time, the front-end camera of the mobile phone is used to shoot the identity card copying part with the two-dimensional code on the surface.
It should be noted that, when the target object is an original of the identification card, the process of acquiring the image of the identification card by using the mobile phone is the same as the above process, and details are not repeated here.
The mapping of the identification mark and the acquisition of the target image can be completed through the mobile phone, the applicability of the image identification method provided by the embodiment of the specification is improved, and further, the actual requirements of each application scene can be met through the mutual matching of the image identification method and the application in the mobile phone.
In an application example, to ensure that a valid target image can be accurately acquired, before acquiring the target image, the method further includes: and detecting the target object.
Acquiring a target image of a target object includes:
and correspondingly acquiring a target image of the target object according to the detection result.
Specifically, before the target image is acquired, the detecting of the target object may include detecting whether the type of the target object meets a preset identification requirement, for example, the identification requirement is an identity card, and detecting whether the target object is an identity card; it may also include detecting whether the target object is in a predetermined position, for example, detecting whether an edge of the target object exceeds the acquisition area.
For example, when detecting whether the type of the target object meets the preset identification requirement, the method may include shooting the target object, obtaining a picture of the target object, and detecting whether the type of the target certificate meeting the preset identification requirement exists on the picture. The type of the target object can be different types of certificates such as an identity card, a driving license and the like, and can also be a bank card.
When the shot picture of the target object is detected, the picture can be detected through a preset target object type detection model, and whether the type of the target object in the picture meets the preset identification requirement or not is determined. For example, based on a neural network model, such as a single shot multi-box detector (SSD) in a convolutional neural network model, a plurality of marked photos including a preset target object type are used as input for training the SSD model, the SSD model is trained, the trained SSD model is used to detect the shot photos of the target object, and it is determined whether the type of the target object meets a preset recognition requirement.
By detecting the type of the target object in advance, the identification failure caused by using a wrong target object in the subsequent identification process is avoided, and the identification efficiency is improved.
For another example, when detecting whether the target object is at the predetermined position, a picture of the target object may be obtained by shooting the target object, and whether the target object in the picture is at the predetermined position may be detected.
When the shot picture of the target object is detected, the neural network model, such as an SSD model in a convolutional neural network model, may also be used to identify the target object in the picture, determine whether the edge of the target object is completely in the picture, use a plurality of marked pictures containing the target object at a predetermined position as the input of a training SSD model to train the SSD model, and then detect the shot picture of the target object by using the trained SSD model to determine whether the target object is at the predetermined position.
Whether the target object is located at the preset position or not is detected, so that the acquired target image can contain the complete target object, namely all parts of the target object are contained in the target image, and omission is avoided to influence subsequent identification.
It should be noted that, the detection of the target object may be performed before the identification mark is mapped, that is, the identification mark is not mapped on the target object to be detected; or the mapping may be performed after the identification mark is mapped, that is, the identification mark is mapped on the target object to be detected.
When the target object is detected before the identification mark is mapped, the picture adopted for training the SSD model contains the target object but does not contain the identification mark.
When the target object is detected after the identification mark is mapped, the photo adopted for training the SSD model simultaneously contains the target object and the identification mark.
In an application example, when the target object is detected after mapping the identification, i.e. the detection of the target object may comprise detecting the target object based on the identification when the identification is mapped on the target object.
For example, when detecting whether the target object is at the predetermined position, detecting the target object based on the identification mark may include positioning by the identification mark, and detecting whether the target object is at the predetermined position based on a relative position of the identification mark and the target object.
In one application example, in order to facilitate determination of the detection result and improve detection efficiency, in the detection target object, a detection instruction is output according to the detection result.
Specifically, sending out a corresponding detection instruction as a prompt message according to the detection result so as to know the detection situation according to the detection instruction and execute subsequent operations.
For example, when qualified target certificates are detected, a qualification indication is sent out to prompt the follow-up operation; and when the qualified target certificate is not detected, sending an unqualified indication to prompt that the target object has errors and needs to be adjusted.
It should be noted that the prompt information can be presented in various different manners, for example, the prompt information can be presented by using lights with different colors, can be presented by using vibrations with different frequencies, and can be presented by using different sounds.
In one application example, in order to adapt to complex detection conditions in practical use, detection instructions are clearly and accurately output, and the detection instructions comprise voice broadcast and/or light instructions.
For example, when the detection instruction is voice broadcast, if a qualified target object is detected, a voice broadcast mode is used for prompting that the target certificate is detected; if the qualified target object is not detected, circularly detecting until overtime, and circularly prompting that the target certificate is not detected in a voice broadcast mode in the process of circularly detecting; and if the time is out, prompting that the target certificate cannot be detected and quitting the time is out in a voice broadcast mode. The target object which is not detected to be qualified may include that the type of the target object does not meet the preset identification requirement, and may include that the target object is not located at the preset position.
The detection instruction is output in a voice prompt mode, so that the whole detection instruction can be clearly output, and the simplicity and convenience of the operation process are improved.
When the detection indication is light, different detection conditions can be prompted by light with different colors or light with different frequencies flickering.
Further, a plurality of target image obtaining manners are preset, and obtaining the target image of the target object according to the detection result after obtaining the detection result may include obtaining the target image according to the obtaining manner corresponding to the detection result, for example, the target image may be automatically captured after detecting a qualified target object, the target image may be captured according to an input capturing instruction after detecting a qualified target object, or the target image may be captured according to an input capturing instruction after detecting a unqualified target object.
In one application example, in order to ensure that the target image is acquired according to the target object qualified for detection, acquiring the target image of the target object includes: and when the qualified target object is detected, acquiring a target image within preset acquisition time.
Specifically, in order to ensure the accuracy of the acquired target image, when a qualified target object is detected, the target image should be acquired in time according to the qualified target object, for example, when the trained SSD model determines that the type of the target object meets a preset identification requirement, the target image may be acquired within 1s after determination, thereby avoiding that the detection result is invalid due to an excessively long interval, and the acquired target image cannot be used, which affects subsequent identification.
It should be noted that, in the embodiment of the present specification, the acquisition time may be preset according to a specific application scenario, and is not specifically limited herein.
The target image is automatically acquired based on the detection result of the target object, so that the effectiveness of the acquired target image can be ensured, the identification efficiency is improved, and the interference of redundant operation on the identification process is avoided.
Step S203, determining the attribute of the target object corresponding to the target image according to the identification feature and the preset mapping relation.
The attribute of the target object may include a category to which the target object belongs.
Taking the target object identity document as an example, when the target object is an original document, the attribute of the target object will be the original document; when the target object is an electronic piece forged from an original of the document, the attribute of the target object will be a copied piece.
The preset mapping relation comprises a corresponding relation between the identification features and the attributes of the target object and is used for identifying the target image, and the attributes of the target object corresponding to the target image are determined according to the identification features, namely whether the target image belongs to an original or a copy is determined. The preset mapping relation can be obtained through a pre-trained reproduction recognition model, and the reproduction recognition model is realized based on a deep learning binary network. Specifically, the two categories include: a reproduction member and an original; when the reproduction recognition model is trained, 500 images respectively marked with classification and containing recognition features are used as input for training. During recognition, the target image obtained in step S203 is input, recognition is performed by copying the recognition model, and the attribute of the target object is determined according to the recognition result.
In the embodiment of the present specification, a target image of a target object is acquired, where before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used to form a corresponding identification feature in the target image, so that a difference generated by the identification mark on the target object is utilized to form an identification feature that can be used for identification on the target image, the identification feature generated based on the difference is actively added to the identification process, and then an attribute of the target object corresponding to the target image is determined according to the identification feature according to a preset mapping relationship, where the mapping relationship includes a corresponding relationship between the identification feature and the attribute of the target object, thereby effectively improving the accuracy of target image identification.
Example 2
In embodiment 2, the same method as that in embodiment 1 is used with the same reference numerals and the same description is omitted.
Fig. 4 is a flowchart of an authentication method according to an embodiment of the present disclosure.
As shown in fig. 4, the authentication method of the embodiment of the present specification includes the following steps:
in step S301, a first target image of a target object is acquired.
Before the first target image is obtained, an identification mark is mapped on the target object, and the identification mark is used for forming a corresponding identification feature in the first target image.
Step S303, determining the attribute of the target object corresponding to the first target image according to the identification characteristics and the preset mapping relation.
The mapping relation comprises a corresponding relation between the identification characteristics and the attributes of the target object.
Step S305 authenticates the target object based on the determination result.
Specifically, when it is determined in step S303 that the first target image is from the original, the target object is authenticated to confirm the authenticity of the target object.
For example, the authentication of the target object may include extracting text information on the target object, comparing the text information with pre-stored information, and determining whether the target object is authentic. The pre-stored information may include pre-filled information, and may include information pre-stored in a third party system.
In an application example, to ensure the accuracy of the authentication process, the method further comprises:
after the first target image is obtained, a second target image of the target object is obtained within a preset time period, wherein the second target image is an image which is not mapped with the identification mark on the target object;
authenticating the target object includes:
processing the second target image according to a preset data processing strategy;
and determining the authenticity of the target object according to the data processing result.
In this embodiment of the present specification, the target object in the second target image is a target object that is not mapped with the identification identifier, so as to avoid the influence of the identification identifier on the target object authentication, and therefore, the acquiring of the second target image may be performed after step S303, at this time, the identification identifier on the target object is removed first, and then the second target image is acquired; it may also be performed before step S303, for example, acquiring a second target image after detecting a qualified target object, in which case the detection of the target object is performed based on the target object without the identification identifier mapped.
For example, the second target image may be acquired for a predetermined period of time after it is determined that the first target image is from the original, and the target image may be acquired within 0.5S after the determination, as when it is determined in step S303 that the first target image is from the original.
The second target image acquisition method avoids the failure of the identification result caused by the overlong interval, ensures the accuracy of the second target image, and simultaneously, the second target image is acquired based on the identification result of the first target image, and the second target image is acquired according to the authentication requirement and is a resource which must be used in the subsequent authentication process, thereby ensuring the effective utilization of the resource.
Further, when the target object is authenticated, the data processing strategy adopted may include processing a second target image including the target object by using an Optical Character Recognition (OCR) technique to recognize and extract information on the second target image, for example, when the target object is an identification card, extracting information such as name, birthday, certificate validity period, etc. on the identification card, and determining the authenticity of the target object according to the extracted information, for example, sending the extracted information on the identification card to a public security system, confirming the authenticity of the information, and further determining the authenticity of the identification card.
The following describes an authentication method provided in this specification, taking as an example a process of authenticating authenticity of an identity card by an authentication application in a mobile phone:
fig. 5 is a flowchart of an authentication method according to an embodiment of the present disclosure.
As shown in fig. 5, the authentication method of the embodiment of the present specification includes the following steps:
in step S401, the mobile phone outputs a detection start instruction, and then executes step S403.
Wherein the detection initiation instruction may include prompting the user to place the credential to be authenticated in the capture area.
The output of the detection start instruction can be in a voice broadcast mode; or a prompt message can be displayed on the screen of the mobile phone.
Step S403, determining whether the certificate is an identity card, if so, executing step S405, otherwise, executing step S407.
In the embodiment of the specification, a certificate is photographed, and the photographed certificate photo is detected by using a trained SSD model, so that whether the certificate is an identity card is judged.
Step S405, displaying the two-dimensional code on the screen of the mobile phone, mapping the two-dimensional code to the identity card, and then executing step S4011.
Step S407, outputting a detection failure instruction by the mobile phone voice, determining whether the detection is overtime, if yes, executing step S409, otherwise, executing step S401.
And step S409, outputting a detection timeout instruction by the mobile phone voice, and ending.
And step S4011, the front camera of the mobile phone shoots a first target image, and then step S4013 is executed.
The first target image comprises an identity card and identification features generated according to a two-dimensional code mapped on the identity card.
Step S4013, determining an attribute of the target object corresponding to the first target image according to the recognition feature and the preset mapping relationship, and if the attribute of the target object corresponding to the first target image is an original of the identification card, executing step S4015.
In the embodiment of the description, the trained reproduction identification model is used for identifying the first target image and confirming whether the identity card is an original.
And step S4015, the mobile phone screen stops displaying the two-dimensional code, the front camera shoots a second target image, and then step S4017 is executed.
Wherein, the second target image only comprises the identity card.
Step S4017, authenticate the identity card, and then end.
In the embodiment of the specification, information such as name, birthday, certificate validity period and the like on the identity card is extracted through an OCR technology, the information is sent to a public security system, the authenticity of the identity card is confirmed, if the information is real, the authentication is passed, and if the information is false, the authentication is failed.
Example 3
Fig. 6 is a schematic structural diagram of an image recognition device according to an embodiment of the present disclosure.
Based on the same application concept, the image recognition device described in the embodiments of the present specification may include:
the acquiring unit 501 is configured to acquire a target image of a target object, where before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used to form a corresponding identification feature in the target image;
the identifying unit 503 determines the attribute of the target object corresponding to the target image according to the identification feature and a preset mapping relationship, where the mapping relationship includes a correspondence relationship between the identification feature and the attribute of the target object.
Optionally, before acquiring the target image, the apparatus further includes: a detection unit that detects the target object,
the acquiring a target image of a target object includes:
and correspondingly acquiring a target image of the target object according to the detection result.
Optionally, the detecting the target object includes: and when the identification mark is mapped on the target object, detecting the target object based on the identification mark.
Optionally, in the detecting the target object, the apparatus further includes: and an output unit which outputs a detection instruction according to the detection result.
Optionally, the correspondingly acquiring the target image of the target object according to the detection result includes: and when the qualified target object is detected, acquiring the target image within preset acquisition time.
Optionally, the apparatus is used in a mobile terminal, and the mobile terminal includes a display unit and an image acquisition unit;
the step of acquiring a target image of the target object includes:
acquiring the target image through the image acquisition unit;
the step of mapping the identification on the target object comprises:
mapping, by the display unit, the recognition identifier presented on the display unit on the target object;
wherein the image acquisition unit and the display unit are located on the same side of the target object.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects: the method comprises the steps of obtaining a target image of a target object, wherein before the target image is obtained, an identification mark is mapped on the target object and is used for forming corresponding identification features in the target image, so that the identification features which can be used for identification are formed on the target image by utilizing the difference generated on the target object by the identification mark, the identification features which are generated based on difference are added to the identification process actively, then the attribute of the target object corresponding to the target image is determined according to the identification features according to a preset mapping relation, and the mapping relation comprises the corresponding relation between the identification features and the attribute of the target object, so that the accuracy of target image identification is effectively improved.
Based on the same inventive concept, embodiments of the present specification further provide an electronic device, including at least one processor and a memory, where the memory stores a program and is configured to be executed by the at least one processor to:
acquiring a target image of a target object, wherein before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used for forming a corresponding identification feature in the target image;
and determining the attribute of the target object corresponding to the target image according to the identification feature and a preset mapping relation, wherein the mapping relation comprises the corresponding relation between the identification feature and the attribute of the target object.
For other functions of the processor, reference may also be made to the contents described in the above embodiments, which are not described in detail herein.
Based on the same inventive concept, embodiments of the present specification further provide a computer-readable storage medium including a program for use in conjunction with an electronic device, the program being executable by a processor to perform the steps of:
acquiring a target image of a target object, wherein before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used for forming a corresponding identification feature in the target image;
and determining the attribute of the target object corresponding to the target image according to the identification feature and a preset mapping relation, wherein the mapping relation comprises the corresponding relation between the identification feature and the attribute of the target object.
Example 4
Fig. 7 is a schematic structural diagram of an authentication apparatus according to an embodiment of the present disclosure.
Based on the same application concept, the authentication device described in the embodiments of the present specification may include:
an acquiring unit 601, configured to acquire a first target image of a target object, where an identification mark is mapped on the target object before the target image is acquired, and the identification mark is used to form a corresponding identification feature in the first target image;
the identifying unit 603 determines an attribute of the target object corresponding to the first target image according to the identification feature and a preset mapping relationship, where the mapping relationship includes a corresponding relationship between the identification feature and the attribute of the target object;
the authentication unit 605 authenticates the target object based on the determination result.
Optionally, the apparatus further comprises:
after the first target image is obtained, obtaining a second target image of the target object in a preset time period, wherein the second target image is an image which is not mapped with the identification mark on the target object;
the authenticating the target object comprises:
processing the second target image according to a preset data processing strategy;
and determining the authenticity of the target object according to the data processing result.
Based on the same inventive concept, embodiments of the present specification further provide an electronic device, including at least one processor and a memory, where the memory stores a program and is configured to be executed by the at least one processor to:
acquiring a first target image of a target object, wherein before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used for forming a corresponding identification feature in the first target image;
determining the attribute of a target object corresponding to the first target image according to the identification feature and a preset mapping relation, wherein the mapping relation comprises the corresponding relation between the identification feature and the attribute of the target object;
and authenticating the target object according to the determined result.
For other functions of the processor, reference may also be made to the contents described in the above embodiments, which are not described in detail herein.
Based on the same inventive concept, embodiments of the present specification further provide a computer-readable storage medium including a program for use in conjunction with an electronic device, the program being executable by a processor to perform the steps of:
acquiring a first target image of a target object, wherein before the target image is acquired, an identification mark is mapped on the target object, and the identification mark is used for forming a corresponding identification feature in the first target image;
determining the attribute of a target object corresponding to the first target image according to the identification feature and a preset mapping relation, wherein the mapping relation comprises the corresponding relation between the identification feature and the attribute of the target object;
and authenticating the target object according to the determined result.
In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.